Remix.run Logo
▲ noduerme 2 hours ago

I love the idea, somehow, that these systems had to be built with domain knowledge integrated into the choices of layers and the order of algorithms, using rather brilliant discoveries for optimizing lines and edges, or whatever was relevant to the problem. That's an order of specificity that's lacking from our modern reliance on "one shot" solutions. Letting a one shot solver grind its brains against creating a custom solution to a specific set of transformations is kind if a closing of the circle when it comes to performance and resources for a certain task.

I'm looking forward to the day we can have an optical device that runs only on light input, that looks like a piece of quartz, that you can place over a handwritten number (0-9) and on the top it displays the number in a clean font. Where the neural network to handle this can be translated into physical transformations once it's discovered, no inference processing power required.

▲andrewbutts an hour ago | parent [-]

Here’s a 2024 project that built a denoiser out of passive optics! https://nips.cc/virtual/2024/poster/95165